Run multiple AI coding agents from one board.
A workstream per session — Claude Code, Codex, Cursor. Queue tasks, connect an agent with a copy-paste prompt, and it pulls work, runs full-auto, and reports back. When one needs you, that column lights up and your browser pings — so you stop hunting across terminals for the one that's stuck.
The AI Agent Task Board is a free board for running several AI coding agents in parallel without losing track. Each column is a workstream — one Claude Code, Codex, or Cursor session. You queue tasks (with full instructions), then connect an agent via a copy-paste prompt + personal API key. The agent pulls its next task, works it autonomously, marks it done, and pulls the next. If it needs you, that column lights up and your browser pings you. No signup to try the board; sign in to connect agents and sync across devices.
From a pile of terminals to one board
Four steps. The first three take a couple of minutes; the fourth is just glancing over while the agents work.
Make a workstream per session
One column = one parallel agent session. Name it after the project or the agent — "autopilot fixes", "landing redesign", "data migration". Run as many as you juggle (up to 24).
Queue tasks with real instructions
Each card has a title plus an instructions field — that body is exactly what the agent receives as its task. Be specific: repo, branch, acceptance criteria, links. The top card is what gets worked next.
Connect an agent (copy-paste once)
Hit "Connect an agent", generate your API key, and copy the bootstrap prompt into a fresh Claude Code / Codex / Cursor session. From then on it self-drives: pull → do → complete → pull the next.
Glance, and jump in when a column lights up
Agents run full-auto. When one genuinely needs your decision, its column turns 🟡 "needs you" and your browser fires a notification — so you stop hunting across terminals for the one that's waiting.
Built for juggling parallel agents
One glance instead of a terminal hunt
Running five or six agent sessions, you forget which is doing what and which is stuck waiting on you. The board is a single map of every parallel stream — status, current task, and queue, all in one place.
Notify-only, so you stay heads-down
Agents work autonomously and only interrupt you when they truly need a decision. The column flips amber and the browser pings — you go to that terminal, answer, and the agent resumes itself.
A queue per stream, not one big pile
Each workstream has its own ordered queue. The agent always takes the top task; finish it, it surfaces the next. "Make next" bumps a card to the front when priorities shift mid-run.
Bring your own agent — no lock-in
It works with anything that can run curl: Claude Code, Codex, Cursor, or your own scripts. The board exposes a tiny REST protocol (pull / attention / resume / complete) behind a personal key scoped to your board.
Frequently asked questions
What is the AI Agent Task Board?
It is a free, browser-based board for managing multiple AI coding agents running in parallel. Each column is a workstream (one agent session); each card is a task with a title and an instructions body. You can use it as a plain manual board, or connect autonomous agents that pull tasks from it and report progress back via a simple API.
Is it free, and do I need to sign up?
The board is free. You can use it anonymously with no signup — it saves to your browser via IndexedDB. To connect autonomous agents (which need a private API key) and to sync your board across devices, sign in with Google.
How do agents actually connect to the board?
Click "Connect an agent" on any workstream, generate your personal API key, and copy the bootstrap prompt it gives you. Paste that into a fresh Claude Code, Codex, or Cursor session. The prompt tells the agent to call the board over HTTPS (with curl): pull its next task, do it, mark it complete, and repeat — fully autonomously.
What happens when an agent gets stuck and needs me?
This is notify-only by design. The agent flags the task, that column turns amber ("needs you"), and your browser fires a notification so you know which terminal to go to. You answer the agent directly at that terminal; it then clears the flag and resumes itself. The board is your at-a-glance signal, not a chat relay.
Is the API key secure?
The key is a long random token shown only once at generation; only a SHA-256 hash is stored. It is scoped strictly to your own board — it can read and write only your workstreams and tasks. Regenerate it anytime (which instantly invalidates the old one). Treat it like a password: keep it out of public repos and shared logs.
Which agents and tools work with it?
Anything that can make an HTTP request. It is built and tested for Claude Code, OpenAI Codex, and Cursor in full-auto mode, but the protocol is plain REST (pull / attention / resume / complete) so your own scripts or any agent framework can drive it too.
Can I run several sessions on the same project?
Yes. Workstreams are independent columns — make as many as you like for one project (e.g. "frontend", "backend", "tests") or spread them across different projects. Each has its own task queue and its own connected agent.
Is my data private?
Anonymous boards never leave your browser. Signed-in boards are stored in Codersera’s database scoped to your account. We never share or sell your data, and never use it to train models. Task instructions are stored as plain text so your agents (and you) can read them back exactly.
Do I have to automate it? Can I just use it as a manual board?
Absolutely use it manually. Plenty of people just want one place to see what each of their parallel agent sessions is doing and tick tasks off by hand. The agent automation is an optional power-up — the board is useful on its own as external memory across sessions.
Stop losing track of your agents.
Spin up a workstream, queue a few tasks, and connect your first agent in under five minutes.
